Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity

Langlais, Philippe; Lapalme, Guy

doi:10.1023/b:coat.0000010117.98933.a0

Cited by 33 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This assumption is in line with experiences gained in a similar translation prediction system, TRANSTYPE (Langlais et al 2004), where it was suggested that "over a longer period [the system] is expected to give a much better picture of its possibilities".…”

Section: Introductionsupporting

confidence: 75%

“…3 in this volume), we have developed an advanced postediting platform with an interactive translation prediction mode, context dependent completions during the translation process (Langlais et al 2004). Even though this feature was designed to help translators in their translation production, within a 3-days field study in a professional translation agency 1 Carl et al (2013) it semed to hamper translators rather than help them to produce faster translations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

New Directions in Empirical Translation Process Research

Carl¹,

Bangalore

Schaeffer³

2016

New Frontiers in Translation Studies

View full text Add to dashboard Cite

Section: Introductionsupporting

confidence: 75%

Section: Introductionmentioning

confidence: 99%

New Directions in Empirical Translation Process Research

Carl¹,

Bangalore

Schaeffer³

2016

New Frontiers in Translation Studies

View full text Add to dashboard Cite

“…Keystroke analysis has been used to judge translators' productivity (Langlais and Lapalme, 2002;Whyman and Somers, 1999). Koponen et al (2012) suggested that post-editing time reflects the cognitive effort in post-editing the MT output.…”

Section: Related Workmentioning

confidence: 99%

Improving translation memory matching and retrieval using paraphrases

Gupta

OrăźSan

Zampieri

et al. 2016

Machine Translation

View full text Add to dashboard Cite

Most of the current Translation Memory (TM) systems work on string level (character or word level) and lack semantic knowledge while matching. They use simple edit-distance calculated on surface-form or some variation on it (stem, lemma), which does not take into consideration any semantic aspects in matching. This paper presents a novel and efficient approach to incorporating semantic information in the form of paraphrasing in the edit-distance metric. The approach computes edit-distance while efficiently considering paraphrases using dynamic programming and greedy approximation. In addition to using automatic evaluation metrics like BLEU and METEOR, we have carried out an extensive human evaluation in which we measured post-editing time, keystrokes, HTER, HMETEOR, and carried out three rounds of subjective evaluations. Our results show that paraphrasing substantially improves TM matching and retrieval, resulting in translation performance increases when translators use paraphrase-enhanced TMs.

show abstract

“…This paper reports on the CAT workbench being developed within the CASMACAT project 1 . Among the different features implemented in the workbench, we will investigate the interactive translation prediction (ITP) approach (Langlais and Lapalme, 2002;Casacuberta et al, 2009;Barrachina et al, 2009). Within the ITP framework, a state-of-the-art statistical machine translation (SMT) system is used in the following way.…”

Section: Introductionmentioning

confidence: 99%

Integrating Online and Active Learning in a Computer-Assisted Translation Workbench

Ortiz-Martínez

González-Rubio²,

Alabau

et al. 2016

New Directions in Empirical Translation Process Research

View full text Add to dashboard Cite

This paper describes a pilot study with a computed-assisted translation workbench aiming at testing the integration of online and active learning features. We investigate the effect of these features on translation productivity, using interactive translation prediction (ITP) as a baseline. User activity data were collected from five beta testers using key-logging and eye-tracking. User feedback was also collected at the end of the experiments in the form of retrospective think-aloud protocols. We found that OL performs better than ITP, especially in terms of translation speed. In addition, AL provides better translation quality than ITP for the same levels of user effort. We plan to incorporate these features in the final version of the workbench.

show abstract

Trans Type: Development-Evaluation Cycles to Boost Translator's Productivity

Cited by 33 publications

References 12 publications

New Directions in Empirical Translation Process Research

New Directions in Empirical Translation Process Research

Improving translation memory matching and retrieval using paraphrases

Integrating Online and Active Learning in a Computer-Assisted Translation Workbench

Contact Info

Product

Resources

About